Evolutionary Interactive Bot for the FPS Unreal Tournament 2004

Size: px
Start display at page:

Download "Evolutionary Interactive Bot for the FPS Unreal Tournament 2004"

Transcription

1 Evolutionary Interactive Bot for the FPS Unreal Tournament 2004 José L. Jiménez 1, Antonio M. Mora 2, Antonio J. Fernández-Leiva 1 1 Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga (Spain). josejl1987@gmail.com,afdez@lcc.uma.es 2 Departamento de Teoría de la Señal, Telemática y Comunicaciones. ETSIIT-CITIC, Universidad de Granada (Spain). amorag@geneura.ugr.es Abstract. This paper presents an interactive genetic algorithm for generating a human-like autonomous player (bot) for the game Unreal Tournament It is based on a bot modelled from the knowledge of an expert human player. The algorithm provides two types of interaction: by an expert in the game and by an expert in the algorithm. Each one affects different aspects of the evolution, directing it towards better results regarding the agent s humanness (objective of this work). It has been conducted an analysis of the experts influence on the performance, showing much better results after these interactions that the non-interactive version. The best bot were submitted to the BotPrize 2014 competition (which seeks for the best human-like bot), getting the second position. 1 Introduction Unreal Tournament 2004[1], also know as UT2004 or UT2K4, is a first person shooter (FPS) game mainly focused on the multiplayer experience, which includes several game modes for promoting this playability. It includes a oneplayer mode in which the rest of team partners (if so) and rivals are controlled by the machine, thus they are autonomous. They are called bots. One of the main contributions of Unreal series is the utilities that the game offers for the gamers to create and share their own creations or modifications on the game contents (mods). These could be new weapons, scenarios, and even new game modes. Most of them are, in turn, more popular among the players than the original ones. They can be created with the editor that the game provides (UnrealED), included with every copy. The Artifical Intelligence (AI) has completely changed in the last years, from the classical set of static behavioural rules (including some random component), the use of Finite State Machines (FSM), or the recent use of Scripts, Navigation Meshes and Behavioural trees. The most extended among the Non-Player Characters (NPC) could be the FSMs [2]. However, nowadays the AI is focused, not only in defining very competitive rivals or partners, but also in the humanness of them. This aims to design be-

2 2 J.L. Jiménez et al. lievable NPCs to which the player can feel empathy, in order to improve his/her experience and lasting appeal about the game. This paper presents a work in this line, proposing an Interactive Genetic Algorithm (IGA) [3] which evolves a bot, previously defined, by modelling the knowledge and tricks of an expert human player, named Expert UnrealBot [4]. The objective is that the bot has a human-like behaviour, rather than just a very competitive bot with a very good performance in the game. This bot has been designed to play in the Deathmatch mode, in which the aim in a match is to reach a number of frags (enemies killed) or the maximum amount of frags in a limited amount of time. There could be just 1 vs 1 player or several players fighting against others. The presented approach includes two types of interaction: the first one is conducted by an expert in the game (expert human player in UT2K4), who can assess the behaviour of the bot considering its humanness; the second type of interaction is done by an expert in the algorithmic part, i.e., he/she can appraise the performance on an individual in the algorithm. We have also defined a parallel approach which can profit the run in a cluster of computers in order to reduce by ten the computational time (which was very expensive). 2 Background and related works 2.1 Turing Test for bots This is a variation of the classical Turing Test in which a human judge who looks and interacts with a virtual world (a game), must to distinguish if the other actors (players) in the game are humans or bots. This test was proposed in order to advance in the fields of Artificial and Computational Intelligence in videogames, since a bot which can pass this test could be considered as excellent, and could increase the quality of the game from the players point of view. Moreover the test tries to prove that the problem of AI for videogames is far from being solved. Aiming to other areas, the methods used in this test could be useful in virtual learning environments and in the improvement of the interaction human-robot (or machines in general). The Turing Test for bots is focused on a mutiplayer gamer in which the bot has to cooperate of fight against other players (humans or bots), making the same decisions that a human would take. This was transformed into an international competition with the features: There will be (ideally) three players: a human player, a bot and a judge. The bot must simulate to be more human than the human player, however the marks are not complementary, i.e. both players can obtain a mark between 1 and 5 (1=Non-human, 5=Human). The three players cannot be distinguished from outside (even with a random name and appearance). Thus, the judge cannot be influenced by these features.

3 Evolutionary Interactive Bot for the FPS Unreal Tournament There is no chat during the match. Bots cannot have omniscient powers as in other games. They can just react to the same stimuli (caught by means of sensors) than a human player. The human player must be an averaged one, in order to avoid very competitive behaviours that could also influence in the judge s decision. In 2008 it was held the first 2K BotPrize competition (BotPrize from now on), in which UT2K4 was considered as the world for this test. The participants should create their human-like bots using an external library to interact with the game by means of TCP connections, named GameBots [5]. The first BotPrize competition considered the Deathmatch mode, and divided the rounds in 10 minutes matches. The judges were the last joining to the matches and observed on player/bot exactly once and none bot was categorised as more human than a human. In the following editions (in 2009, 2010 and 2011) the marks of the bots were improved, however they still were not able to overcome to any of the human players. Anyway, the maximum humanness score for the human players was just 41.4 %. This demonstrates the limitations of the test (or the competition), since even appraise a human behaviour is a quite complex task. 2.2 Human-like bots The winners of BotPrize 2012 were UTˆ2Bot [6] and MirrorBot [7]. The first one was created by a team of the University of Texas. This bot is based in two main ideas: the application of multiobjective neural evolution in order to use just those combat actions which seem to be human-conducted and a proper navigation of the map. They used stored logs of human plays in order to optimize both objectives. MirrorBot was created by Mihai Polceanu (a PhD student in the LAB-STICC, ENIB). It basically imitates the reactions of the opponent, using interactive techniques. The idea is that if a judge is close to the bot it would imitate his/her behaviour, which could clearly mislead the judge and make him/her thinking that the player is showing a human-like behaviour. Obviously this technique is not useful if the opponent is another bot. The bot we are presenting here is named NizorBot, and it is an improved version of our previous ExpertBot [4]. The aim of the latter was the modelling of the behaviour of an expert Spanish human player (one of the authors), who participated in international UT2K4 contests. It included a two-level FSM, in which the main states define the high level behaviour of the bot (such as attack o retreat), meanwhile the secondary states (or substates) can modify this behaviour in order to meet immediate or necessary objectives (such as taking health packages or a powerful weapon that is close to the bot s position). The decisions about the states is made by an expert system, based in a huge amount of rules considering almost all the conditions (and tricks) that a human expert would do. It also uses a memory (a database) to retain important information about the fighting arena, such as the position of items and weapons, or advantageous points. This information is stored once the bot has discovered them, as a human player would do.

4 4 J.L. Jiménez et al. ExpertBot is formed by two layers: The first one is the cognitive layer, in charge of controlling the FSM considering the environmental stimuli (perceived by sensors). It decides the transitions between states and substates using the expert system and the memory (database). The second one is the reactive layer, which does not perform any kind of reasoning, and just react immediately to events during the match. 3 Methodology Human intervention for guiding the optimisation process has proved to be very effective improving, not only the quality of the solution, but also the performance of the algorithm itself for finding the solution to a problem [8]. This improvement is specially needed for problems where the subjectivity is part of the evaluation process. This is typical of problems which involve human creativity (such as generative art), or those which aims to increase the human satisfaction or challenge (such as content generation in games). However, the interaction in an optimisation algorithm could be conducted in many different ways and could affect to many different aspects of the approach. On the one hand, the participation of an expert in problem scope would be key in order to measure the quality of a candidate solution. On the other hand, an expert in the algorithmic scope could improve the overall performance of the approach or could direct the search/optimization process to promising areas of the space of solutions [9]. Even though these methods perform very well, interactive algorithms are not very common since they have some flaws, including the human tiredness or boringness if the expert has to intervene several times (which should be, in turn, ideally). The usual solution [10] consists in adapting the algorithm to be more proactive, so it could predict somehow the decisions that the human will take about a candidate solution. Another approach is based in the extrapolation of the decisions taken by the human, so similar solutions (closer in Euclidean distance for instance) would receive automatically a similar value. However this approach depends on the problem definition and on the structure of the solutions, since close solutions in the space of solutions should be really similar in the problem scope. In this work, we propose an Interactive Genetic Algorithm (IGA)[3], in which the experts guide the optimization of the ExpertBot parameters in order to obtain a human-like bot. We think that this intervention is very relevant in order to value the candidate solutions (i.e. bots) regarding something as subjective as the humanness of an autonomous agent in a game. In the following sections the algorithm and the points of interaction are described.

5 Evolutionary Interactive Bot for the FPS Unreal Tournament Chromosome structure Every individual in the GA is a chromosome with 26 genes, divided in 6 blocks of information. The description of each block is: Distance selection block. Set of parameters which control the distance ranges that the agent considers to attack with one specific type of weapon, and also the distances to the enemy both for attacking it or for defending from it. Gene 0 : Short distance. Value between 0 and Gene 1 : Medium distance. Value between the current value for Gene 0 and Gene 2 : Far distance. Value between the current value for Gene 1 and Weapon selection block. Set of parameters which control the priority assigned to every weapon considering some factors, such as distance to enemy, altitude where the enemy is, and the physical location of the agent with respect to the enemy. Genes 3-11: They control the priority associated to every weapon. Values between 0 and 100. Health control block. Set of parameters which control the level of health of the bot, depending on which it will be offencive, defencive or neutral. Gene 12: If the health level is lower than this, the bot will be defencive. Value between 0 and 100. Gene 13: If the health level is lower than this, the bot will be neutral. Value between the current value for Gene 12 and 160. Risk block. Set of parameters which control the amount of health points that the bot could risk. Gene 14: Value between 5 and 30. Gene 15: Value between 15 and 80. Gene 16: Value between 15 and 60. Gene 17: Value between 10 and 120. Gene 18: Value between 20 and 100. Time block. Gene which defines the amount of time which the agent considers to decide that the enemy is out of vision/perception. Gene 19: Value between 3 and 9 seconds. Item control block. Set of parameters which control the priority assigned to the most important items and weapons. As higher the value is, higher the priority will be for timing the item/weapon (i.e. control of its respawn time). Gen 20: Priority of Super Shield Pack. Value between 0 and 100. Gen 21: Priority of Shield Pack. Value between 0 and 100. Gen 22: Priority of Lightning Gun. Value between 0 and 100. Gen 23: Priority of Shock Rifle. Value between 0 and 100. Gen 24: Priority of Flak Cannon and of Rocket Launcher. Value between 0 and 100. Gen 25: Priority of Minigun. Value between 0 and 100.

6 6 J.L. Jiménez et al. 3.2 Fitness and evaluation The fitness function is defined as: (fr d) + s2 + s1 2 +log((dmgg dmgt ) + 1) f(fr, d, dmgg, dmgt, s1, s2) = fr d + s2 + s1 2 +log((dmgg dmgt ) + 1) if fr d if fr < d Where fr is the number of enemy kills the bot has obtained (frags), d is the number of own deads, dmgg is the total damage produced by the bot, and dmgt is the total damage it has received. s1 and s2 refers respectively to the number of Shields and Super Shields the bot has picked up (very important item). This function rewards the individuals with a positive balance (more frags than deads) and a high number of frags. In addition individuals which perform a high amount of damage to the enemies are also rewarded, even if they have not got a good balance. The logarithms are used due to the magnitude that the damages take, being around the thousand. We add 1 to avoid negative values. Normally the fitness functions must be less complex, in this case, just considering overall the number of frags and deads. However, we have decided to consider several factors to value the performance of a bot, above all, the gathering and use of items, as they are very important in the matches in UT2K4. The evaluation of an individual consists in setting the values of the chromosome in the NizorBot AI engine, then a 1 vs 1 combat is launched between this and a standard UT2K4 bot in its maximum difficulty level (they are more robust and reliable). Once the time defined for the match is finished, the summary of the individual (bot) performance regarding these values is considered for the fitness computation. There is a high pseudo-stochastic component in these battles to take into account, since the results do not depend completely on our bot, but also on the enemy s actions which we cannot control. Thus, the fitness function is considered as noisy [11], since an individual could be valued as good in one combat, but yield very bad results in another match. This problem will be addressed in future works. 3.3 Selection and Genetic Operators A probability roulette wheel has been used as selection mechanism, considering the fitness value as a proportion of this probability. The elitism has been implemented by replacing the five worst individuals of the new population by the five best of the current one. The uniform crossover operator, so every gene of a descendent has the same probability of belonging to each one of the parents.

7 Evolutionary Interactive Bot for the FPS Unreal Tournament Interactive Evaluations The interaction of the game expert has been conducted just stopping in some specific points of the evolution (in some generations). Then, a form with several questions is presented to him/her. It can be seen in Figure 1. Fig. 1. Interactive evaluation form This form shows the data about the best individual of the current generation (and thus, the best overall due to elitism). The expert can watch a video of the corresponding bot playing a match (using the number of generation and bot s ID). After the visualisation of the record, the evaluator must fill in the form, checking the boxes which better describe the behaviour he/she has seen in the video. Every checkbox is associated to a set of genes of the chromosome, so, if the expert thinks that there is a good behaviour in any sense this would be translated into the algorithm by freezing (or blocking) the corresponding genes in the chromosome of the best. This will affect the rest of the population when this individual combines and spreads its genetic material. Thus, this interaction will also reduce the search space, so the algorithm performance will be improved. The algorithm then continues the run until a new stopping point is reached. The interaction of the algorithm expert is done by just studying the fitness evolution plotted in graphs in the software Graphic User Interface and changing the parameter values of the GA. Thus, he/she can affect the evolutionary process increasing the crossover or mutation probability, for instance. 3.5 Parallel Architecture The evaluation of every bot/individual is very expensive in time (around 150 minutes per generation), since a match must be played almost in real time due to UT2K4 does not permit accelerating the game without provoking secondary effects, such as bad collision detections. For this reason, we have implemented a parallel version of the algorithm, in which several individuals are evaluated at the same time (running the matches

8 8 J.L. Jiménez et al. in different machines), following a client/server architecture. We have used the extension of Pogamut [12] which let the programmer to launch matches in command line with the desired options, also including the bots with the corresponding chromosome values. Once the match has ended, the bot (client) sends the summary/statistics to the server, in order to compute a fitness value for that bot. If there is an error during a match, the server will be aware of this and can reinitialise the match. 4 Analysis of results This section is devoted to analyse the performance of our proposals. To do so, we have consider the same map DM-ironic and a generational interactive genetic algorithm with population size 30, number of generations 50, mutation variation 10%, mutation probability 0.33%, uniform crossover and crossover probability 1.0, elitist replacement policy keeping the 5th best candidates from the previous generation. Interaction with the human expert is forced at specific generations; three versions were considered depending on the number of interactions: 1 interaction (forced at generation 25), 2 interactions (forced at generations 16 and 33), and 4 interactions (forced at generations 10,20,30 and 40). We have also considered a version with no human interaction. Five runs per algorithm, and 5 minutes for each evaluation were executed. Figure 2 shows the results obtained by these four variations of algorithm. As interactivity increases, the results gets more consistent. Anyway, this can be the result of fixing some parts of the chromosome encoding. The consequence might be that candidates are more similar and with equivalent fitness. 4.1 Humanity evaluation To evaluate the adequacy of our proposal, our bot competed in the 2K Bot- Prize competition 3 (edition 2014) that proposes the Turing test in UT2K4. This competition has been sponsored by 2K Australia. In the original competition, the evaluation of the humanity of bots was in charge of a number of judges that participated directly in the matches; this means a First Person Assessment (FPA). In the edition of 2014, a Third Person Assessment (TPA) was included by means of the participation of (external) judges via a crowdsourcing platform. The general schema of the new evaluation is shown in Figure 3 which shows the function to calculate the Humanness value (H) of a bot taking into account the FPA and TPA. In addition, since 2014, this competition proposes a second challenge that evaluates the own skill of the bots to be able to judge the humanity of the other bots. However, this is not an objective for our bot. The results of the reliability evaluation (both by humans and also bots) is shown in Figure

9 Evolutionary Interactive Bot for the FPS Unreal Tournament Fig. 2. Fitness comparison. In all box plots, the red line indicates the median of the distribution, whereas the bottom and top of the box correspond respectively to the first and third quartile of the distribution. Fig. 3. Evaluation system considered in BotPrize 2014

10 10 J.L. Jiménez et al. Fig. 4. Results of detection of bots (reliability) in Botprize 2014 As it can be seen in Figures 5 and 6, the winner of this edition was Mirrorbot (the same as in previous editions), which was one of the two bots that passed the Turing test adapted to games in the previous editions of the competition (so that it can be considered the state-of-the-art). However, as result of the new (and harder) evaluation system, it does no reach the value for being consider human (i.e., 0.5) although is relatively close to it. Out bot (NizorBot) show a very good performance finishing as the runner-up and with a humanity factor relatively close to be considered as human. it was programmed taking into account the patterns of behaviour of an expert human player in Unreal Tournament 2004, and this might explain its success. Fig. 5. Results of Botprize 2014(I)

11 Evolutionary Interactive Bot for the FPS Unreal Tournament Fig. 6. Results of Botprize 2014(II) 5 Conclusions and future work This paper describes a genetic algorithm-based proposal to create a Non-Player Character (bot) that plays, in a human-style, the game Unreal Tournament Some user-centric proposals (i.e., with human interaction) have been proposed and compared with a non-interactive version. All the proposals perform similarly if they are compared according only to the score (i.e., fitness) obtained during a number of matches; however, according to a humanity factor the incorporation of interactivity provides very good results, and this has been proved via the results obtained by one of our human-guided algorithms in the context of the 2K BotPrize competition. There is room for many improvements: for instance, the schema of navigation in our bots might be improved. In addition, currently the fitness function that guides the search process introduce noise in the optimisation process, and we believe that the incorporation of several human experts in the guidance of our algorithms surely would produce more consistent results. Acknowledgements This work has been partially supported by project V of the Microprojects program 2015 from CEI BioTIC Granada, Junta de Andalucía within the project P10-TIC-6083 (DNEMESIS 4 ), by Ministerio de Ministerio español de Economía y Competitividad under (preselected as granted) project TIN C4-1- P (UMA-EPHEMECH), and Universidad de Málaga. Campus de Excelencia Internacional Andalucía Tech. 4

12 12 J.L. Jiménez et al. References 1. Unreal tournament (2014) 2. Arbib, M.A.: Theories of abstract automata. Prentice-Hall (1969) 3. Sims, K.: Artificial evolution for computer graphics. ACM SIGGRAPH Computer Graphics 25(4) (1991) Mora, A., Aisa, F., Caballero, R., García-Sánchez, P., Merelo, J., Castillo, P., Lara-Cabrera, R.: Designing and evolving an unreal tournamenttm 2004 expert bot. Springer (2013) WEB: Gamebots project (2008) 6. Schrum, J., Karpov, I.V., Miikkulainen, R.: Ut? 2: Human-like behavior via neuroevolution of combat behavior and replay of human traces. (2011) Polceanu, M.: Mirrorbot: Using human-inspired mirroring behavior to pass a turing test. (2013) Klau, G., Lesh, N., Marks, J., Mitzenmacher, M.: Human-guided search. Journal of Heuristics 16 (2010) Cotta, C., Leiva, A.J.F.: Bio-inspired combinatorial optimization: Notes on reactive and proactive interaction. In Cabestany, J., Rojas, I., Caparrós, G.J., eds.: Advances in Computational Intelligence - 11th International Work-Conference on Artificial Neural Networks, IWANN 2011, Part II. Volume 6692 of Lecture Notes in Computer Science., Springer (2011) Badillo, A.R., Ruiz, J.J., Cotta, C., Leiva, A.J.F.: On user-centric memetic algorithms. Soft Comput. 17(2) (2013) Mora, A.M., Fernández-Ares, A., Merelo, J.J., García-Sánchez, P., Fernandes, C.M.: Effect of noisy fitness in real-time strategy games player behaviour optimisation using evolutionary algorithms. J. Comput. Sci. Technol. 27(5) (2012) Pogamut - virtual characters made easy about (2014) 13. Dyer, D.: The watchmaker framework for evolutionary computation (evolutionary/genetic algorithms for java) (2014) machine.unizar.es/: Human-like bots competition 2014 (2014) Xstream - about xstream (2014)

Improving the Performance of a Computer-Controlled Player in a Maze Chase Game using Evolutionary Programming on a Finite-State Machine

Improving the Performance of a Computer-Controlled Player in a Maze Chase Game using Evolutionary Programming on a Finite-State Machine Improving the Performance of a Computer-Controlled Player in a Maze Chase Game using Evolutionary Programming on a Finite-State Machine Maximiliano Miranda and Federico Peinado Departamento de Ingeniería

More information

Designing Competitive Bots for a Real Time Strategy Game using Genetic Programming

Designing Competitive Bots for a Real Time Strategy Game using Genetic Programming Designing Competitive Bots for a Real Time Strategy Game using Genetic Programming A. Fernández-Ares, P. García-Sánchez, A.M. Mora, P.A. Castillo, and J.J. Merelo Dept. of Computer Architecture and Computer

More information

Evolving Multimodal Behavior Through Subtask and Switch Neural Networks

Evolving Multimodal Behavior Through Subtask and Switch Neural Networks Evolving Multimodal Behavior Through Subtask and Switch Neural Networks Xun Li 1 and Risto Miikkulainen 1 1 The University of Texas at Austin xun.bhsfer@utexas.edu Abstract While neuroevolution has been

More information

City University of Hong Kong

City University of Hong Kong City University of Hong Kong Information on a Course offered by Department of Computer Science with effect from Semester A in 2014 / 2015 Part I Course Title: AI Game Programming Course Code: CS4386 Course

More information

UTˆ2: Human-like Behavior via Neuroevolution of Combat Behavior and Replay of Human Traces

UTˆ2: Human-like Behavior via Neuroevolution of Combat Behavior and Replay of Human Traces UTˆ2: Human-like Behavior via Neuroevolution of Combat Behavior and Replay of Human Traces Jacob Schrum, Igor V. Karpov and Risto Miikkulainen Abstract The UTˆ2 bot, which had a humanness rating of 27.2727%

More information

SEED 2013 PRIMER SIMPOSIO ESPAÑOL DE ENTRETENIMIENTO DIGITAL 18 Y 19 DE SEPTIEMBRE DE 2013 UNIVERSIDAD COMPLUTENSE DE MADRID SEED @ CEDI 2013 ACTAS DE

SEED 2013 PRIMER SIMPOSIO ESPAÑOL DE ENTRETENIMIENTO DIGITAL 18 Y 19 DE SEPTIEMBRE DE 2013 UNIVERSIDAD COMPLUTENSE DE MADRID SEED @ CEDI 2013 ACTAS DE ACTAS DE SEED 2013 PRIMER SIMPOSIO ESPAÑOL DE ENTRETENIMIENTO DIGITAL UNIVERSIDAD COMPLUTENSE DE MADRID 18 Y 19 DE SEPTIEMBRE DE 2013 SEED @ CEDI 2013 El primer foro científico para el intercambio de ideas

More information

D A T A M I N I N G C L A S S I F I C A T I O N

D A T A M I N I N G C L A S S I F I C A T I O N D A T A M I N I N G C L A S S I F I C A T I O N FABRICIO VOZNIKA LEO NARDO VIA NA INTRODUCTION Nowadays there is huge amount of data being collected and stored in databases everywhere across the globe.

More information

Gerard Mc Nulty Systems Optimisation Ltd gmcnulty@iol.ie/0876697867 BA.,B.A.I.,C.Eng.,F.I.E.I

Gerard Mc Nulty Systems Optimisation Ltd gmcnulty@iol.ie/0876697867 BA.,B.A.I.,C.Eng.,F.I.E.I Gerard Mc Nulty Systems Optimisation Ltd gmcnulty@iol.ie/0876697867 BA.,B.A.I.,C.Eng.,F.I.E.I Data is Important because it: Helps in Corporate Aims Basis of Business Decisions Engineering Decisions Energy

More information

Evolutionary SAT Solver (ESS)

Evolutionary SAT Solver (ESS) Ninth LACCEI Latin American and Caribbean Conference (LACCEI 2011), Engineering for a Smart Planet, Innovation, Information Technology and Computational Tools for Sustainable Development, August 3-5, 2011,

More information

Programming Risk Assessment Models for Online Security Evaluation Systems

Programming Risk Assessment Models for Online Security Evaluation Systems Programming Risk Assessment Models for Online Security Evaluation Systems Ajith Abraham 1, Crina Grosan 12, Vaclav Snasel 13 1 Machine Intelligence Research Labs, MIR Labs, http://www.mirlabs.org 2 Babes-Bolyai

More information

Automatic Gameplay Testing for Message Passing Architectures

Automatic Gameplay Testing for Message Passing Architectures Automatic Gameplay Testing for Message Passing Architectures Jennifer Hernández Bécares, Luis Costero Valero and Pedro Pablo Gómez Martín Facultad de Informática, Universidad Complutense de Madrid. 28040

More information

New Modifications of Selection Operator in Genetic Algorithms for the Traveling Salesman Problem

New Modifications of Selection Operator in Genetic Algorithms for the Traveling Salesman Problem New Modifications of Selection Operator in Genetic Algorithms for the Traveling Salesman Problem Radovic, Marija; and Milutinovic, Veljko Abstract One of the algorithms used for solving Traveling Salesman

More information

A Robust Method for Solving Transcendental Equations

A Robust Method for Solving Transcendental Equations www.ijcsi.org 413 A Robust Method for Solving Transcendental Equations Md. Golam Moazzam, Amita Chakraborty and Md. Al-Amin Bhuiyan Department of Computer Science and Engineering, Jahangirnagar University,

More information

School of Computer Science

School of Computer Science School of Computer Science Computer Science - Honours Level - 2014/15 October 2014 General degree students wishing to enter 3000- level modules and non- graduating students wishing to enter 3000- level

More information

Genetic Algorithms commonly used selection, replacement, and variation operators Fernando Lobo University of Algarve

Genetic Algorithms commonly used selection, replacement, and variation operators Fernando Lobo University of Algarve Genetic Algorithms commonly used selection, replacement, and variation operators Fernando Lobo University of Algarve Outline Selection methods Replacement methods Variation operators Selection Methods

More information

Modified Version of Roulette Selection for Evolution Algorithms - the Fan Selection

Modified Version of Roulette Selection for Evolution Algorithms - the Fan Selection Modified Version of Roulette Selection for Evolution Algorithms - the Fan Selection Adam S lowik, Micha l Bia lko Department of Electronic, Technical University of Koszalin, ul. Śniadeckich 2, 75-453 Koszalin,

More information

Behavior Capture with Acting Graph: a Knowledgebase for a Game AI System

Behavior Capture with Acting Graph: a Knowledgebase for a Game AI System Behavior Capture with Acting Graph: a Knowledgebase for a Game AI System Maxim Mozgovoy 1* and Iskander Umarov 2, 1 University of Aizu, Tsuruga, Ikki-machi, Aizu-Wakamatsu, Fukushima, 965-8580 Japan mozgovoy@u-aizu.ac.jp

More information

Artificial Intelligence (AI)

Artificial Intelligence (AI) Overview Artificial Intelligence (AI) A brief introduction to the field. Won t go too heavily into the theory. Will focus on case studies of the application of AI to business. AI and robotics are closely

More information

About the Author. The Role of Artificial Intelligence in Software Engineering. Brief History of AI. Introduction 2/27/2013

About the Author. The Role of Artificial Intelligence in Software Engineering. Brief History of AI. Introduction 2/27/2013 About the Author The Role of Artificial Intelligence in Software Engineering By: Mark Harman Presented by: Jacob Lear Mark Harman is a Professor of Software Engineering at University College London Director

More information

Asexual Versus Sexual Reproduction in Genetic Algorithms 1

Asexual Versus Sexual Reproduction in Genetic Algorithms 1 Asexual Versus Sexual Reproduction in Genetic Algorithms Wendy Ann Deslauriers (wendyd@alumni.princeton.edu) Institute of Cognitive Science,Room 22, Dunton Tower Carleton University, 25 Colonel By Drive

More information

Establishing How Many VoIP Calls a Wireless LAN Can Support Without Performance Degradation

Establishing How Many VoIP Calls a Wireless LAN Can Support Without Performance Degradation Establishing How Many VoIP Calls a Wireless LAN Can Support Without Performance Degradation ABSTRACT Ángel Cuevas Rumín Universidad Carlos III de Madrid Department of Telematic Engineering Ph.D Student

More information

Management of Software Projects with GAs

Management of Software Projects with GAs MIC05: The Sixth Metaheuristics International Conference 1152-1 Management of Software Projects with GAs Enrique Alba J. Francisco Chicano Departamento de Lenguajes y Ciencias de la Computación, Universidad

More information

GA as a Data Optimization Tool for Predictive Analytics

GA as a Data Optimization Tool for Predictive Analytics GA as a Data Optimization Tool for Predictive Analytics Chandra.J 1, Dr.Nachamai.M 2,Dr.Anitha.S.Pillai 3 1Assistant Professor, Department of computer Science, Christ University, Bangalore,India, chandra.j@christunivesity.in

More information

14.10.2014. Overview. Swarms in nature. Fish, birds, ants, termites, Introduction to swarm intelligence principles Particle Swarm Optimization (PSO)

14.10.2014. Overview. Swarms in nature. Fish, birds, ants, termites, Introduction to swarm intelligence principles Particle Swarm Optimization (PSO) Overview Kyrre Glette kyrrehg@ifi INF3490 Swarm Intelligence Particle Swarm Optimization Introduction to swarm intelligence principles Particle Swarm Optimization (PSO) 3 Swarms in nature Fish, birds,

More information

An Overview of Knowledge Discovery Database and Data mining Techniques

An Overview of Knowledge Discovery Database and Data mining Techniques An Overview of Knowledge Discovery Database and Data mining Techniques Priyadharsini.C 1, Dr. Antony Selvadoss Thanamani 2 M.Phil, Department of Computer Science, NGM College, Pollachi, Coimbatore, Tamilnadu,

More information

Web Mining using Artificial Ant Colonies : A Survey

Web Mining using Artificial Ant Colonies : A Survey Web Mining using Artificial Ant Colonies : A Survey Richa Gupta Department of Computer Science University of Delhi ABSTRACT : Web mining has been very crucial to any organization as it provides useful

More information

Grid Computing for Artificial Intelligence

Grid Computing for Artificial Intelligence Grid Computing for Artificial Intelligence J.M.P. van Waveren May 25th 2007 2007, Id Software, Inc. Abstract To show intelligent behavior in a First Person Shooter (FPS) game an Artificial Intelligence

More information

Using Data Mining for Mobile Communication Clustering and Characterization

Using Data Mining for Mobile Communication Clustering and Characterization Using Data Mining for Mobile Communication Clustering and Characterization A. Bascacov *, C. Cernazanu ** and M. Marcu ** * Lasting Software, Timisoara, Romania ** Politehnica University of Timisoara/Computer

More information

Genetic Algorithm. Based on Darwinian Paradigm. Intrinsically a robust search and optimization mechanism. Conceptual Algorithm

Genetic Algorithm. Based on Darwinian Paradigm. Intrinsically a robust search and optimization mechanism. Conceptual Algorithm 24 Genetic Algorithm Based on Darwinian Paradigm Reproduction Competition Survive Selection Intrinsically a robust search and optimization mechanism Slide -47 - Conceptual Algorithm Slide -48 - 25 Genetic

More information

Practical Applications of Evolutionary Computation to Financial Engineering

Practical Applications of Evolutionary Computation to Financial Engineering Hitoshi Iba and Claus C. Aranha Practical Applications of Evolutionary Computation to Financial Engineering Robust Techniques for Forecasting, Trading and Hedging 4Q Springer Contents 1 Introduction to

More information

Optimum Design of Worm Gears with Multiple Computer Aided Techniques

Optimum Design of Worm Gears with Multiple Computer Aided Techniques Copyright c 2008 ICCES ICCES, vol.6, no.4, pp.221-227 Optimum Design of Worm Gears with Multiple Computer Aided Techniques Daizhong Su 1 and Wenjie Peng 2 Summary Finite element analysis (FEA) has proved

More information

Game Design From Concepts To Implementation

Game Design From Concepts To Implementation Game Design From Concepts To Implementation Overview of a Game Engine What is a Game Engine? (Really) Technical description of game: A Soft real-time interactive agent-based computer simulation A game

More information

A Systemic Artificial Intelligence (AI) Approach to Difficult Text Analytics Tasks

A Systemic Artificial Intelligence (AI) Approach to Difficult Text Analytics Tasks A Systemic Artificial Intelligence (AI) Approach to Difficult Text Analytics Tasks Text Analytics World, Boston, 2013 Lars Hard, CTO Agenda Difficult text analytics tasks Feature extraction Bio-inspired

More information

Developing an Artificial Intelligence Engine

Developing an Artificial Intelligence Engine Introduction Developing an Artificial Intelligence Engine Michael van Lent and John Laird Artificial Intelligence Lab University of Michigan 1101 Beal Ave. Ann Arbor, MI 48109-2110 {vanlent,laird}@umich.edu

More information

CS Master Level Courses and Areas COURSE DESCRIPTIONS. CSCI 521 Real-Time Systems. CSCI 522 High Performance Computing

CS Master Level Courses and Areas COURSE DESCRIPTIONS. CSCI 521 Real-Time Systems. CSCI 522 High Performance Computing CS Master Level Courses and Areas The graduate courses offered may change over time, in response to new developments in computer science and the interests of faculty and students; the list of graduate

More information

[Name of the game] Game Design Document. Created by [Name of the team]:

[Name of the game] Game Design Document. Created by [Name of the team]: [Name of the game] Game Design Document Created by [Name of the team]: [Name of each team member] [Company logo] [Company name] [Date] Table of content 1 Overview... 4 1.1 Game abstract... 4 1.2 Objectives

More information

Ch 1: What is Game Programming Really Like? Ch 2: What s in a Game? Quiz #1 Discussion

Ch 1: What is Game Programming Really Like? Ch 2: What s in a Game? Quiz #1 Discussion Ch 1: What is Game Programming Really Like? Ch 2: What s in a Game? Quiz #1 Discussion Developing a Game Game Architecture Resources: Chapter 2 (Game Coding Complete) What was your last game architecture

More information

the gamedesigninitiative at cornell university Lecture 5 Rules and Mechanics

the gamedesigninitiative at cornell university Lecture 5 Rules and Mechanics Lecture 5 Rules and Mechanics Today s Lecture Reading is from Unit 2 of Rules of Play Available from library as e-book Linked to from lecture page Not required, but excellent resource Important for serious

More information

Handling Big(ger) Logs: Connecting ProM 6 to Apache Hadoop

Handling Big(ger) Logs: Connecting ProM 6 to Apache Hadoop Handling Big(ger) Logs: Connecting ProM 6 to Apache Hadoop Sergio Hernández 1, S.J. van Zelst 2, Joaquín Ezpeleta 1, and Wil M.P. van der Aalst 2 1 Department of Computer Science and Systems Engineering

More information

Keywords revenue management, yield management, genetic algorithm, airline reservation

Keywords revenue management, yield management, genetic algorithm, airline reservation Volume 4, Issue 1, January 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A Revenue Management

More information

ISSN: 2319-5967 ISO 9001:2008 Certified International Journal of Engineering Science and Innovative Technology (IJESIT) Volume 2, Issue 3, May 2013

ISSN: 2319-5967 ISO 9001:2008 Certified International Journal of Engineering Science and Innovative Technology (IJESIT) Volume 2, Issue 3, May 2013 Transistor Level Fault Finding in VLSI Circuits using Genetic Algorithm Lalit A. Patel, Sarman K. Hadia CSPIT, CHARUSAT, Changa., CSPIT, CHARUSAT, Changa Abstract This paper presents, genetic based algorithm

More information

Optimization in Strategy Games: Using Genetic Algorithms to Optimize City Development in FreeCiv

Optimization in Strategy Games: Using Genetic Algorithms to Optimize City Development in FreeCiv Abstract Optimization in Strategy Games: Using Genetic Algorithms to Optimize City Development in FreeCiv Ian Watson,, Ya Chuyang, Wei Pan & Gary Chen There is a growing demand for the use of AI techniques

More information

Unnatural Gaming. Checkmate. Project Definition. SEG 4000 Dr. Liam Peyton. Revision #: 03 Revision Date: January 29, 2003

Unnatural Gaming. Checkmate. Project Definition. SEG 4000 Dr. Liam Peyton. Revision #: 03 Revision Date: January 29, 2003 Unnatural Gaming Checkmate Project Definition SEG 4 Dr. Liam Peyton Revision #: 3 Revision Date: January 29, 23 Ashraf Ismail Jacques Lebrun Bretton MacLean Rahwa Keleta Table of Contents 1. Title... 2

More information

University of Portsmouth PORTSMOUTH Hants UNITED KINGDOM PO1 2UP

University of Portsmouth PORTSMOUTH Hants UNITED KINGDOM PO1 2UP University of Portsmouth PORTSMOUTH Hants UNITED KINGDOM PO1 2UP This Conference or Workshop Item Adda, Mo, Kasassbeh, M and Peart, Amanda (2005) A survey of network fault management. In: Telecommunications

More information

Study of Various Load Balancing Techniques in Cloud Environment- A Review

Study of Various Load Balancing Techniques in Cloud Environment- A Review International Journal of Computer Sciences and Engineering Open Access Review Paper Volume-4, Issue-04 E-ISSN: 2347-2693 Study of Various Load Balancing Techniques in Cloud Environment- A Review Rajdeep

More information

MEng, BSc Applied Computer Science

MEng, BSc Applied Computer Science School of Computing FACULTY OF ENGINEERING MEng, BSc Applied Computer Science Year 1 COMP1212 Computer Processor Effective programming depends on understanding not only how to give a machine instructions

More information

A Non-Linear Schema Theorem for Genetic Algorithms

A Non-Linear Schema Theorem for Genetic Algorithms A Non-Linear Schema Theorem for Genetic Algorithms William A Greene Computer Science Department University of New Orleans New Orleans, LA 70148 bill@csunoedu 504-280-6755 Abstract We generalize Holland

More information

Applying Design Patterns in Distributing a Genetic Algorithm Application

Applying Design Patterns in Distributing a Genetic Algorithm Application Applying Design Patterns in Distributing a Genetic Algorithm Application Nick Burns Mike Bradley Mei-Ling L. Liu California Polytechnic State University Computer Science Department San Luis Obispo, CA

More information

FIoT: A Framework for Self-Adaptive and Self-Organizing Internet of Things Applications. Nathalia Moraes do Nascimento nnascimento@inf.puc-rio.

FIoT: A Framework for Self-Adaptive and Self-Organizing Internet of Things Applications. Nathalia Moraes do Nascimento nnascimento@inf.puc-rio. FIoT: A Framework for Self-Adaptive and Self-Organizing Internet of Things Applications Nathalia Moraes do Nascimento nnascimento@inf.puc-rio.br Roadmap Motivation FIoT Main Idea Application Scenario Decentralized

More information

Improving Decision Making and Managing Knowledge

Improving Decision Making and Managing Knowledge Improving Decision Making and Managing Knowledge Decision Making and Information Systems Information Requirements of Key Decision-Making Groups in a Firm Senior managers, middle managers, operational managers,

More information

Introduction To Genetic Algorithms

Introduction To Genetic Algorithms 1 Introduction To Genetic Algorithms Dr. Rajib Kumar Bhattacharjya Department of Civil Engineering IIT Guwahati Email: rkbc@iitg.ernet.in References 2 D. E. Goldberg, Genetic Algorithm In Search, Optimization

More information

A Framework for Genetic Algorithms in Games

A Framework for Genetic Algorithms in Games A Framework for Genetic Algorithms in Games Vinícius Godoy de Mendonça Cesar Tadeu Pozzer Roberto Tadeu Raiitz 1 Universidade Positivo, Departamento de Informática 2 Universidade Federal de Santa Maria,

More information

Decomposition into Parts. Software Engineering, Lecture 4. Data and Function Cohesion. Allocation of Functions and Data. Component Interfaces

Decomposition into Parts. Software Engineering, Lecture 4. Data and Function Cohesion. Allocation of Functions and Data. Component Interfaces Software Engineering, Lecture 4 Decomposition into suitable parts Cross cutting concerns Design patterns I will also give an example scenario that you are supposed to analyse and make synthesis from The

More information

Genetic Algorithms for Energy Efficient Virtualized Data Centers

Genetic Algorithms for Energy Efficient Virtualized Data Centers Genetic Algorithms for Energy Efficient Virtualized Data Centers 6th International DMTF Academic Alliance Workshop on Systems and Virtualization Management: Standards and the Cloud Helmut Hlavacs, Thomas

More information

Alpha Cut based Novel Selection for Genetic Algorithm

Alpha Cut based Novel Selection for Genetic Algorithm Alpha Cut based Novel for Genetic Algorithm Rakesh Kumar Professor Girdhar Gopal Research Scholar Rajesh Kumar Assistant Professor ABSTRACT Genetic algorithm (GA) has several genetic operators that can

More information

Table of Contents 11-step plan on how to get the most out of the strategies backtesting... 2 Step #1... 2 Pick any strategy you like from the "10

Table of Contents 11-step plan on how to get the most out of the strategies backtesting... 2 Step #1... 2 Pick any strategy you like from the 10 Table of Contents 11-step plan on how to get the most out of the strategies backtesting... 2 Step #1... 2 Pick any strategy you like from the "10 simple free strategies" file... 2 Step #2... 2 Get a strict

More information

NEUROEVOLUTION OF AUTO-TEACHING ARCHITECTURES

NEUROEVOLUTION OF AUTO-TEACHING ARCHITECTURES NEUROEVOLUTION OF AUTO-TEACHING ARCHITECTURES EDWARD ROBINSON & JOHN A. BULLINARIA School of Computer Science, University of Birmingham Edgbaston, Birmingham, B15 2TT, UK e.robinson@cs.bham.ac.uk This

More information

Bachelor Degree in Informatics Engineering Master courses

Bachelor Degree in Informatics Engineering Master courses Bachelor Degree in Informatics Engineering Master courses Donostia School of Informatics The University of the Basque Country, UPV/EHU For more information: Universidad del País Vasco / Euskal Herriko

More information

Masters in Artificial Intelligence

Masters in Artificial Intelligence Masters in Artificial Intelligence Programme Requirements Taught Element, and PG Diploma in Artificial Intelligence: 120 credits: IS5101 CS5001 CS5010 CS5011 CS4402 or CS5012 in total, up to 30 credits

More information

MEng, BSc Computer Science with Artificial Intelligence

MEng, BSc Computer Science with Artificial Intelligence School of Computing FACULTY OF ENGINEERING MEng, BSc Computer Science with Artificial Intelligence Year 1 COMP1212 Computer Processor Effective programming depends on understanding not only how to give

More information

APPLICATION OF ADVANCED SEARCH- METHODS FOR AUTOMOTIVE DATA-BUS SYSTEM SIGNAL INTEGRITY OPTIMIZATION

APPLICATION OF ADVANCED SEARCH- METHODS FOR AUTOMOTIVE DATA-BUS SYSTEM SIGNAL INTEGRITY OPTIMIZATION APPLICATION OF ADVANCED SEARCH- METHODS FOR AUTOMOTIVE DATA-BUS SYSTEM SIGNAL INTEGRITY OPTIMIZATION Harald Günther 1, Stephan Frei 1, Thomas Wenzel, Wolfgang Mickisch 1 Technische Universität Dortmund,

More information

QoS Issues for Multiplayer Gaming

QoS Issues for Multiplayer Gaming QoS Issues for Multiplayer Gaming By Alex Spurling 7/12/04 Introduction Multiplayer games are becoming large part of today s digital entertainment. As more game players gain access to high-speed internet

More information

CURRICULUM VITAE EDUCATION:

CURRICULUM VITAE EDUCATION: CURRICULUM VITAE Jose Antonio Lozano Computer Science and Software Development / Game and Simulation Programming Program Chair 1902 N. Loop 499 Harlingen, TX 78550 Computer Sciences Building Office Phone:

More information

Performance evaluation of Web Information Retrieval Systems and its application to e-business

Performance evaluation of Web Information Retrieval Systems and its application to e-business Performance evaluation of Web Information Retrieval Systems and its application to e-business Fidel Cacheda, Angel Viña Departament of Information and Comunications Technologies Facultad de Informática,

More information

Using Emergent Behavior to Improve AI in Video Games

Using Emergent Behavior to Improve AI in Video Games Noname manuscript No. (will be inserted by the editor) Using Emergent Behavior to Improve AI in Video Games Janne Parkkila Received: 21.01.2011 / Accepted: date Abstract Artificial Intelligence is becoming

More information

DDS-Enabled Cloud Management Support for Fast Task Offloading

DDS-Enabled Cloud Management Support for Fast Task Offloading DDS-Enabled Cloud Management Support for Fast Task Offloading IEEE ISCC 2012, Cappadocia Turkey Antonio Corradi 1 Luca Foschini 1 Javier Povedano-Molina 2 Juan M. Lopez-Soler 2 1 Dipartimento di Elettronica,

More information

CSC384 Intro to Artificial Intelligence

CSC384 Intro to Artificial Intelligence CSC384 Intro to Artificial Intelligence What is Artificial Intelligence? What is Intelligence? Are these Intelligent? CSC384, University of Toronto 3 What is Intelligence? Webster says: The capacity to

More information

Masters in Human Computer Interaction

Masters in Human Computer Interaction Masters in Human Computer Interaction Programme Requirements Taught Element, and PG Diploma in Human Computer Interaction: 120 credits: IS5101 CS5001 CS5040 CS5041 CS5042 or CS5044 up to 30 credits from

More information

Lab 4: 26 th March 2012. Exercise 1: Evolutionary algorithms

Lab 4: 26 th March 2012. Exercise 1: Evolutionary algorithms Lab 4: 26 th March 2012 Exercise 1: Evolutionary algorithms 1. Found a problem where EAs would certainly perform very poorly compared to alternative approaches. Explain why. Suppose that we want to find

More information

Effect of Using Neural Networks in GA-Based School Timetabling

Effect of Using Neural Networks in GA-Based School Timetabling Effect of Using Neural Networks in GA-Based School Timetabling JANIS ZUTERS Department of Computer Science University of Latvia Raina bulv. 19, Riga, LV-1050 LATVIA janis.zuters@lu.lv Abstract: - The school

More information

Intelligent Modeling of Sugar-cane Maturation

Intelligent Modeling of Sugar-cane Maturation Intelligent Modeling of Sugar-cane Maturation State University of Pernambuco Recife (Brazil) Fernando Buarque de Lima Neto, PhD Salomão Madeiro Flávio Rosendo da Silva Oliveira Frederico Bruno Alexandre

More information

Intrusion Detection System using Log Files and Reinforcement Learning

Intrusion Detection System using Log Files and Reinforcement Learning Intrusion Detection System using Log Files and Reinforcement Learning Bhagyashree Deokar, Ambarish Hazarnis Department of Computer Engineering K. J. Somaiya College of Engineering, Mumbai, India ABSTRACT

More information

Architecture bits. (Chromosome) (Evolved chromosome) Downloading. Downloading PLD. GA operation Architecture bits

Architecture bits. (Chromosome) (Evolved chromosome) Downloading. Downloading PLD. GA operation Architecture bits A Pattern Recognition System Using Evolvable Hardware Masaya Iwata 1 Isamu Kajitani 2 Hitoshi Yamada 2 Hitoshi Iba 1 Tetsuya Higuchi 1 1 1-1-4,Umezono,Tsukuba,Ibaraki,305,Japan Electrotechnical Laboratory

More information

Application of the Artificial Society Approach to Multiplayer Online Games: A Case Study on Effects of a Robot Rental Mechanism

Application of the Artificial Society Approach to Multiplayer Online Games: A Case Study on Effects of a Robot Rental Mechanism Application of the Artificial Society Approach to Multiplayer Online Games: A Case Study on Effects of a Robot Rental Mechanism Ruck Thawonmas and Takeshi Yagome Intelligent Computer Entertainment Laboratory

More information

Leran Wang and Tom Kazmierski {lw04r,tjk}@ecs.soton.ac.uk

Leran Wang and Tom Kazmierski {lw04r,tjk}@ecs.soton.ac.uk BMAS 2005 VHDL-AMS based genetic optimization of a fuzzy logic controller for automotive active suspension systems Leran Wang and Tom Kazmierski {lw04r,tjk}@ecs.soton.ac.uk Outline Introduction and system

More information

Masters in Human Computer Interaction

Masters in Human Computer Interaction Masters in Human Computer Interaction Programme Requirements Taught Element, and PG Diploma in Human Computer Interaction: 120 credits: IS5101 CS5001 CS5040 CS5041 CS5042 or CS5044 up to 30 credits from

More information

Evolutionary Algorithms Software

Evolutionary Algorithms Software Evolutionary Algorithms Software Prof. Dr. Rudolf Kruse Pascal Held {kruse,pheld}@iws.cs.uni-magdeburg.de Otto-von-Guericke-Universität Magdeburg Fakultät für Informatik Institut für Wissens- und Sprachverarbeitung

More information

Masters in Advanced Computer Science

Masters in Advanced Computer Science Masters in Advanced Computer Science Programme Requirements Taught Element, and PG Diploma in Advanced Computer Science: 120 credits: IS5101 CS5001 up to 30 credits from CS4100 - CS4450, subject to appropriate

More information

Brink Windows Dedicated Server Guide

Brink Windows Dedicated Server Guide Brink Windows Dedicated Server Guide Table of Contents 1.1. Initial Setup... 2 1.1.1. Port Mappings... 2 1.1.2. Thread Limiting... 2 1.2. Launching the Server... 2 1.2.1. Dedicated Server.bat Files...

More information

DURING a project s lifecycle many factors can change at

DURING a project s lifecycle many factors can change at Proceedings of the 2014 Federated Conference on Computer Science and Information Systems pp. 1191 1196 DOI: 10.15439/2014F426 ACSIS, Vol. 2 Algorithms for Automating Task Delegation in Project Management

More information

SERENITY Pattern-based Software Development Life-Cycle

SERENITY Pattern-based Software Development Life-Cycle SERENITY Pattern-based Software Development Life-Cycle Francisco Sanchez-Cid, Antonio Maña Computer Science Department University of Malaga. Spain {cid, amg}@lcc.uma.es Abstract Most of current methodologies

More information

DM810 Computer Game Programming II: AI. Lecture 11. Decision Making. Marco Chiarandini

DM810 Computer Game Programming II: AI. Lecture 11. Decision Making. Marco Chiarandini DM810 Computer Game Programming II: AI Lecture 11 Marco Chiarandini Department of Mathematics & Computer Science University of Southern Denmark Resume Decision trees State Machines Behavior trees Fuzzy

More information

Masters in Networks and Distributed Systems

Masters in Networks and Distributed Systems Masters in Networks and Distributed Systems Programme Requirements Taught Element, and PG Diploma in Networks and Distributed Systems: 120 credits: IS5101 CS5001 CS5021 CS4103 or CS5023 in total, up to

More information

Understanding Proactive vs. Reactive Methods for Fighting Spam. June 2003

Understanding Proactive vs. Reactive Methods for Fighting Spam. June 2003 Understanding Proactive vs. Reactive Methods for Fighting Spam June 2003 Introduction Intent-Based Filtering represents a true technological breakthrough in the proper identification of unwanted junk email,

More information

Learning is a very general term denoting the way in which agents:

Learning is a very general term denoting the way in which agents: What is learning? Learning is a very general term denoting the way in which agents: Acquire and organize knowledge (by building, modifying and organizing internal representations of some external reality);

More information

NAIS: A Calibrated Immune Inspired Algorithm to solve Binary Constraint Satisfaction Problems

NAIS: A Calibrated Immune Inspired Algorithm to solve Binary Constraint Satisfaction Problems NAIS: A Calibrated Immune Inspired Algorithm to solve Binary Constraint Satisfaction Problems Marcos Zuñiga 1, María-Cristina Riff 2 and Elizabeth Montero 2 1 Projet ORION, INRIA Sophia-Antipolis Nice,

More information

Laboratory work in AI: First steps in Poker Playing Agents and Opponent Modeling

Laboratory work in AI: First steps in Poker Playing Agents and Opponent Modeling Laboratory work in AI: First steps in Poker Playing Agents and Opponent Modeling Avram Golbert 01574669 agolbert@gmail.com Abstract: While Artificial Intelligence research has shown great success in deterministic

More information

Expanding the CASEsim Framework to Facilitate Load Balancing of Social Network Simulations

Expanding the CASEsim Framework to Facilitate Load Balancing of Social Network Simulations Expanding the CASEsim Framework to Facilitate Load Balancing of Social Network Simulations Amara Keller, Martin Kelly, Aaron Todd 4 June 2010 Abstract This research has two components, both involving the

More information

Evaluation of Different Task Scheduling Policies in Multi-Core Systems with Reconfigurable Hardware

Evaluation of Different Task Scheduling Policies in Multi-Core Systems with Reconfigurable Hardware Evaluation of Different Task Scheduling Policies in Multi-Core Systems with Reconfigurable Hardware Mahyar Shahsavari, Zaid Al-Ars, Koen Bertels,1, Computer Engineering Group, Software & Computer Technology

More information

A Proposed Case for the Cloud Software Engineering in Security

A Proposed Case for the Cloud Software Engineering in Security A Proposed Case for the Cloud Software Engineering in Security Victor Chang and Muthu Ramachandran School of Computing, Creative Technologies and Engineering, Leeds Metropolitan University, Headinley,

More information

Evaluating Software Products - A Case Study

Evaluating Software Products - A Case Study LINKING SOFTWARE DEVELOPMENT PHASE AND PRODUCT ATTRIBUTES WITH USER EVALUATION: A CASE STUDY ON GAMES Özge Bengur 1 and Banu Günel 2 Informatics Institute, Middle East Technical University, Ankara, Turkey

More information

Imitating human playing styles in Super Mario Bros

Imitating human playing styles in Super Mario Bros Imitating human playing styles in Super Mario Bros Juan Ortega, Noor Shaker, Julian Togelius and Georgios N. Yannakakis IT University of Copenhagen Rued Langgaards Vej 7 2300 Copenhagen, Denmark {juor,

More information

Distributed Database for Environmental Data Integration

Distributed Database for Environmental Data Integration Distributed Database for Environmental Data Integration A. Amato', V. Di Lecce2, and V. Piuri 3 II Engineering Faculty of Politecnico di Bari - Italy 2 DIASS, Politecnico di Bari, Italy 3Dept Information

More information

Artificial Intelligence Beating Human Opponents in Poker

Artificial Intelligence Beating Human Opponents in Poker Artificial Intelligence Beating Human Opponents in Poker Stephen Bozak University of Rochester Independent Research Project May 8, 26 Abstract In the popular Poker game, Texas Hold Em, there are never

More information

2IOE0 Interactive Intelligent Systems

2IOE0 Interactive Intelligent Systems 2IOE0 Interactive Intelligent Systems Erik de Vink, Huub van de Wetering TU/e 2015-2016 Erik de Vink, Huub van de Wetering (TU/e) 2IOE0 Interactive Intelligent Systems 2015-2016 1 / 19 Introduction Course

More information

A Client-Server Interactive Tool for Integrated Artificial Intelligence Curriculum

A Client-Server Interactive Tool for Integrated Artificial Intelligence Curriculum A Client-Server Interactive Tool for Integrated Artificial Intelligence Curriculum Diane J. Cook and Lawrence B. Holder Department of Computer Science and Engineering Box 19015 University of Texas at Arlington

More information

6.2.8 Neural networks for data mining

6.2.8 Neural networks for data mining 6.2.8 Neural networks for data mining Walter Kosters 1 In many application areas neural networks are known to be valuable tools. This also holds for data mining. In this chapter we discuss the use of neural

More information

CyberNEXS Global Services

CyberNEXS Global Services CyberNEXS Global Services CYBERSECURITY A cyber training, exercising, competition and certification product for maximizing the cyber skills of your workforce The Cyber Network EXercise System CyberNEXS

More information

HYBRID GENETIC ALGORITHMS FOR SCHEDULING ADVERTISEMENTS ON A WEB PAGE

HYBRID GENETIC ALGORITHMS FOR SCHEDULING ADVERTISEMENTS ON A WEB PAGE HYBRID GENETIC ALGORITHMS FOR SCHEDULING ADVERTISEMENTS ON A WEB PAGE Subodha Kumar University of Washington subodha@u.washington.edu Varghese S. Jacob University of Texas at Dallas vjacob@utdallas.edu

More information

3D Android game Hide-n-Seek

3D Android game Hide-n-Seek International Journal of Computer Sciences and Engineering Open Access Technical Paper Volume-4, Issue-4 E-ISSN: 2347-2693 3D Android game Hide-n-Seek Sanket Tilotkar 1, Mehul Makwana 2, Siraj Sayyed 3

More information